Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    clarification and defining existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꮦ
    0.44
    Methyl
    0.43
    ስማ
    0.43
     conversión
    0.42
    нев
    0.42
     Católica
    0.42
     niest
    0.42
     zwycię
    0.41
     Fáb
    0.41
     réalise
    0.41
    POSITIVE LOGITS
    2
    0.48
    ("
    0.44
    م
    0.41
     contains
    0.41
     clarification
    0.40
    Package
    0.40
    info
    0.39
     information
    0.39
    agem
    0.38
     by
    0.38
    Act Density 0.003%

    No Known Activations